Automatic fall detection and activity classification by a wearable camera

Koray Ozcan, Anvith Mahabalagiri, Senem Velipasalar

Research output: Chapter in Book/Report/Conference proceedingChapter

4 Citations (Scopus)

Abstract

Automated monitoring of everyday physical activities of elderly has come a long way in the past two decades. These activities might range from critical events such as falls requiring rapid and robust detection to classifying daily activities such as walking, sitting and lying down for long term prognosis. Researchers have constantly strived to come up with innovative methods based on different sensor systems in order to build a robust automated system. These sensor systems can be broadly classified into wearable and ambient sensors. Various vision and non-vision based sensors have been employed in the process. Most popular wearable sensors employ non-vision based sensors such as accelerometers and gyroscopes and have the advantage of not being confined to restricted environments. But resource limitations leave them vulnerable to false positives and render the task of classifying activities very challenging. On the other hand, popular ambient vision based sensors like wall mounted cameras which have resource capabilities for better activity classification are confined to a specific monitoring environment and by nature raise privacy concerns. Recently, integrated wearable sensor systems with accelerometers and camera on a single device have been introduced wherein the camera is used to provide contextual information in order to validate the accelerometer readings. In this chapter, a new idea of using a smart camera as a waist worn fall detection and activity classification system is presented. Therefore, a methodology to classify sitting and lying down activities with such a system is introduced in order to further substantiate the concept of event detection and activity classification with wearable smart cameras.

Original languageEnglish (US)
Title of host publicationDistributed Embedded Smart Cameras: Architectures, Design and Applications
PublisherSpringer New York
Pages151-172
Number of pages22
ISBN (Print)9781461477051, 1461477042, 9781461477044
DOIs
StatePublished - May 1 2014

Fingerprint

Cameras
Sensors
Accelerometers
Monitoring
Gyroscopes
Wearable sensors

ASJC Scopus subject areas

  • Engineering(all)
  • Computer Science(all)

Cite this

Ozcan, K., Mahabalagiri, A., & Velipasalar, S. (2014). Automatic fall detection and activity classification by a wearable camera. In Distributed Embedded Smart Cameras: Architectures, Design and Applications (pp. 151-172). Springer New York. https://doi.org/10.1007/978-1-4614-7705-1_7

Automatic fall detection and activity classification by a wearable camera. / Ozcan, Koray; Mahabalagiri, Anvith; Velipasalar, Senem.

Distributed Embedded Smart Cameras: Architectures, Design and Applications. Springer New York, 2014. p. 151-172.

Research output: Chapter in Book/Report/Conference proceedingChapter

Ozcan, K, Mahabalagiri, A & Velipasalar, S 2014, Automatic fall detection and activity classification by a wearable camera. in Distributed Embedded Smart Cameras: Architectures, Design and Applications. Springer New York, pp. 151-172. https://doi.org/10.1007/978-1-4614-7705-1_7
Ozcan K, Mahabalagiri A, Velipasalar S. Automatic fall detection and activity classification by a wearable camera. In Distributed Embedded Smart Cameras: Architectures, Design and Applications. Springer New York. 2014. p. 151-172 https://doi.org/10.1007/978-1-4614-7705-1_7
Ozcan, Koray ; Mahabalagiri, Anvith ; Velipasalar, Senem. / Automatic fall detection and activity classification by a wearable camera. Distributed Embedded Smart Cameras: Architectures, Design and Applications. Springer New York, 2014. pp. 151-172
@inbook{379ec626a992472c94fd82a1373a9b31,
title = "Automatic fall detection and activity classification by a wearable camera",
abstract = "Automated monitoring of everyday physical activities of elderly has come a long way in the past two decades. These activities might range from critical events such as falls requiring rapid and robust detection to classifying daily activities such as walking, sitting and lying down for long term prognosis. Researchers have constantly strived to come up with innovative methods based on different sensor systems in order to build a robust automated system. These sensor systems can be broadly classified into wearable and ambient sensors. Various vision and non-vision based sensors have been employed in the process. Most popular wearable sensors employ non-vision based sensors such as accelerometers and gyroscopes and have the advantage of not being confined to restricted environments. But resource limitations leave them vulnerable to false positives and render the task of classifying activities very challenging. On the other hand, popular ambient vision based sensors like wall mounted cameras which have resource capabilities for better activity classification are confined to a specific monitoring environment and by nature raise privacy concerns. Recently, integrated wearable sensor systems with accelerometers and camera on a single device have been introduced wherein the camera is used to provide contextual information in order to validate the accelerometer readings. In this chapter, a new idea of using a smart camera as a waist worn fall detection and activity classification system is presented. Therefore, a methodology to classify sitting and lying down activities with such a system is introduced in order to further substantiate the concept of event detection and activity classification with wearable smart cameras.",
author = "Koray Ozcan and Anvith Mahabalagiri and Senem Velipasalar",
year = "2014",
month = "5",
day = "1",
doi = "10.1007/978-1-4614-7705-1_7",
language = "English (US)",
isbn = "9781461477051",
pages = "151--172",
booktitle = "Distributed Embedded Smart Cameras: Architectures, Design and Applications",
publisher = "Springer New York",

}

TY - CHAP

T1 - Automatic fall detection and activity classification by a wearable camera

AU - Ozcan, Koray

AU - Mahabalagiri, Anvith

AU - Velipasalar, Senem

PY - 2014/5/1

Y1 - 2014/5/1

N2 - Automated monitoring of everyday physical activities of elderly has come a long way in the past two decades. These activities might range from critical events such as falls requiring rapid and robust detection to classifying daily activities such as walking, sitting and lying down for long term prognosis. Researchers have constantly strived to come up with innovative methods based on different sensor systems in order to build a robust automated system. These sensor systems can be broadly classified into wearable and ambient sensors. Various vision and non-vision based sensors have been employed in the process. Most popular wearable sensors employ non-vision based sensors such as accelerometers and gyroscopes and have the advantage of not being confined to restricted environments. But resource limitations leave them vulnerable to false positives and render the task of classifying activities very challenging. On the other hand, popular ambient vision based sensors like wall mounted cameras which have resource capabilities for better activity classification are confined to a specific monitoring environment and by nature raise privacy concerns. Recently, integrated wearable sensor systems with accelerometers and camera on a single device have been introduced wherein the camera is used to provide contextual information in order to validate the accelerometer readings. In this chapter, a new idea of using a smart camera as a waist worn fall detection and activity classification system is presented. Therefore, a methodology to classify sitting and lying down activities with such a system is introduced in order to further substantiate the concept of event detection and activity classification with wearable smart cameras.

AB - Automated monitoring of everyday physical activities of elderly has come a long way in the past two decades. These activities might range from critical events such as falls requiring rapid and robust detection to classifying daily activities such as walking, sitting and lying down for long term prognosis. Researchers have constantly strived to come up with innovative methods based on different sensor systems in order to build a robust automated system. These sensor systems can be broadly classified into wearable and ambient sensors. Various vision and non-vision based sensors have been employed in the process. Most popular wearable sensors employ non-vision based sensors such as accelerometers and gyroscopes and have the advantage of not being confined to restricted environments. But resource limitations leave them vulnerable to false positives and render the task of classifying activities very challenging. On the other hand, popular ambient vision based sensors like wall mounted cameras which have resource capabilities for better activity classification are confined to a specific monitoring environment and by nature raise privacy concerns. Recently, integrated wearable sensor systems with accelerometers and camera on a single device have been introduced wherein the camera is used to provide contextual information in order to validate the accelerometer readings. In this chapter, a new idea of using a smart camera as a waist worn fall detection and activity classification system is presented. Therefore, a methodology to classify sitting and lying down activities with such a system is introduced in order to further substantiate the concept of event detection and activity classification with wearable smart cameras.

UR - http://www.scopus.com/inward/record.url?scp=84929566605&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929566605&partnerID=8YFLogxK

U2 - 10.1007/978-1-4614-7705-1_7

DO - 10.1007/978-1-4614-7705-1_7

M3 - Chapter

AN - SCOPUS:84929566605

SN - 9781461477051

SN - 1461477042

SN - 9781461477044

SP - 151

EP - 172

BT - Distributed Embedded Smart Cameras: Architectures, Design and Applications

PB - Springer New York

ER -